lmcoleman/Ornith-1.5-35B-A3B-MagicQuant-GGUF

Quantization vs ornith-ai/Ornith-1.5-35B-A3B. lmcoleman/Ornith-1.5-35B-A3B-MagicQuant-GGUF is a GGUF quantization (Q6_K/Q8_0) of the same weights: 200 tensors match exactly and 143 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/200, Attention 0/40, lm_head 0/1

On the Hub · Downloads on Model Pulse